Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the beginning of text or document sections, specifically marked by a start or initialization token

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or markup fragments

    np_acts-logits-general · gemini-2.0-flash

    Dial tone, mobile devices, information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.71
    AndEndTag
    -0.69
     utafitiHapana
    -0.58
    RefNanny
    -0.57
     ioutil
    -0.53
    ystic
    -0.52
     ویکی‌پدیای
    -0.51
    Enllaces
    -0.51
    Notae
    -0.51
     ویکی‌پدیا
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.63
    CopyWith
    0.58
     للمعارف
    0.55
    =?";
    0.55
    Advertisements
    0.54
    msup
    0.52
    Personensuche
    0.51
    favorited
    0.49
    yntaxException
    0.49
    Према
    0.49
    Act Density 0.055%

    No Known Activations